© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 7-GEMMASCOPE-RES-16K
    11. 14916
    Prev
    Next
    INDEX
    Explanations

    terms related to domestic and sexual violence, including their victims and the context surrounding abusive relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dafx
    -0.56
    jestic
    -0.54
     Stakes
    -0.52
    Cola
    -0.51
    iculous
    -0.50
    limat
    -0.50
    Encyklopedia
    -0.50
    verk
    -0.50
     minde
    -0.49
    ixon
    -0.49
    POSITIVE LOGITS
     abusive
    0.64
     violence
    0.64
     abuse
    0.63
     domestic
    0.63
     bruises
    0.61
    violence
    0.59
    MockMvc
    0.58
     beat
    0.58
    ThroughAttribute
    0.57
    Violence
    0.56
    Activations Density 0.323%

    No Known Activations